workbench 0.8.192__py3-none-any.whl → 0.8.197__py3-none-any.whl

workbench/model_scripts/uq_models/mapie.template

@@ -14,7 +14,7 @@ import joblib
 import os
 import numpy as np
 import pandas as pd
-from typing import List, Tuple
+from typing import List, Tuple, Optional, Dict
 
 # Template Placeholders
 TEMPLATE_PARAMS = {
@@ -26,6 +26,46 @@ TEMPLATE_PARAMS = {
 }
 
 
+def compute_confidence(
+        df: pd.DataFrame,
+        median_interval_width: float,
+        lower_q: str = "q_10",
+        upper_q: str = "q_90",
+        alpha: float = 1.0,
+        beta: float = 1.0,
+) -> pd.DataFrame:
+    """
+    Compute confidence scores (0.0 to 1.0) based on prediction interval width
+    and distance from median using exponential decay.
+
+    Args:
+        df: DataFrame with 'prediction', 'q_50', and quantile columns
+        median_interval_width: Pre-computed median interval width from training data
+        lower_q: Lower quantile column name (default: 'q_10')
+        upper_q: Upper quantile column name (default: 'q_90')
+        alpha: Weight for interval width term (default: 1.0)
+        beta: Weight for distance from median term (default: 1.0)
+
+    Returns:
+        DataFrame with added 'confidence' column
+    """
+    # Interval width
+    interval_width = (df[upper_q] - df[lower_q]).abs()
+
+    # Distance from median, normalized by interval width
+    distance_from_median = (df['prediction'] - df['q_50']).abs()
+    normalized_distance = distance_from_median / (interval_width + 1e-6)
+
+    # Cap the distance penalty at 1.0
+    normalized_distance = np.minimum(normalized_distance, 1.0)
+
+    # Confidence using exponential decay
+    interval_term = interval_width / median_interval_width
+    df['confidence'] = np.exp(-(alpha * interval_term + beta * normalized_distance))
+
+    return df
+
+
 # Function to check if dataframe is empty
 def check_dataframe(df: pd.DataFrame, df_name: str) -> None:
     """
@@ -98,7 +138,7 @@ def convert_categorical_types(df: pd.DataFrame, features: list, category_mapping
 
 
 def decompress_features(
-    df: pd.DataFrame, features: List[str], compressed_features: List[str]
+        df: pd.DataFrame, features: List[str], compressed_features: List[str]
 ) -> Tuple[pd.DataFrame, List[str]]:
     """Prepare features for the model by decompressing bitstring features
 
@@ -302,6 +342,46 @@ if __name__ == "__main__":
         widths = y_pis[:, 1, 0] - y_pis[:, 0, 0]
         print(f"  {conf_level * 100:.0f}% CI: Mean width={np.mean(widths):.3f}, Std={np.std(widths):.3f}")
 
+    # Compute normalization statistics for confidence calculation
+    print(f"\nComputing normalization statistics for confidence scores...")
+
+    # Create a temporary validation dataframe with predictions
+    temp_val_df = df_val.copy()
+    temp_val_df["prediction"] = xgb_model.predict(X_validate)
+
+    # Add all quantile predictions
+    for conf_level in confidence_levels:
+        model_name = f"mapie_{conf_level:.2f}"
+        model = mapie_models[model_name]
+        y_pred, y_pis = model.predict_interval(X_validate)
+
+        if conf_level == 0.50:
+            temp_val_df["q_25"] = y_pis[:, 0, 0]
+            temp_val_df["q_75"] = y_pis[:, 1, 0]
+            # y_pred is the median prediction
+            temp_val_df["q_50"] = y_pred
+        elif conf_level == 0.68:
+            temp_val_df["q_16"] = y_pis[:, 0, 0]
+            temp_val_df["q_84"] = y_pis[:, 1, 0]
+        elif conf_level == 0.80:
+            temp_val_df["q_10"] = y_pis[:, 0, 0]
+            temp_val_df["q_90"] = y_pis[:, 1, 0]
+        elif conf_level == 0.90:
+            temp_val_df["q_05"] = y_pis[:, 0, 0]
+            temp_val_df["q_95"] = y_pis[:, 1, 0]
+        elif conf_level == 0.95:
+            temp_val_df["q_025"] = y_pis[:, 0, 0]
+            temp_val_df["q_975"] = y_pis[:, 1, 0]
+
+    # Compute normalization stats using q_10 and q_90 (default range)
+    interval_width = (temp_val_df["q_90"] - temp_val_df["q_10"]).abs()
+    median_interval_width = float(interval_width.median())
+    print(f"  Median interval width (q_10-q_90): {median_interval_width:.6f}")
+
+    # Save median interval width for confidence calculation
+    with open(os.path.join(args.model_dir, "median_interval_width.json"), "w") as fp:
+        json.dump(median_interval_width, fp)
+
     # Save the trained XGBoost model
     joblib.dump(xgb_model, os.path.join(args.model_dir, "xgb_model.joblib"))
 
@@ -365,11 +445,19 @@ def model_fn(model_dir) -> dict:
         with open(category_path) as fp:
             category_mappings = json.load(fp)
 
+    # Load median interval width for confidence calculation
+    median_interval_width = None
+    median_width_path = os.path.join(model_dir, "median_interval_width.json")
+    if os.path.exists(median_width_path):
+        with open(median_width_path) as fp:
+            median_interval_width = json.load(fp)
+
     return {
         "xgb_model": xgb_model,
         "mapie_models": mapie_models,
         "confidence_levels": config["confidence_levels"],
         "category_mappings": category_mappings,
+        "median_interval_width": median_interval_width,
     }
 
 
@@ -449,6 +537,8 @@ def predict_fn(df, models) -> pd.DataFrame:
         if conf_level == 0.50:  # 50% CI
             df["q_25"] = y_pis[:, 0, 0]
             df["q_75"] = y_pis[:, 1, 0]
+            # y_pred is the median prediction
+            df["q_50"] = y_pred
         elif conf_level == 0.68:  # 68% CI
             df["q_16"] = y_pis[:, 0, 0]
             df["q_84"] = y_pis[:, 1, 0]
@@ -462,14 +552,11 @@ def predict_fn(df, models) -> pd.DataFrame:
             df["q_025"] = y_pis[:, 0, 0]
             df["q_975"] = y_pis[:, 1, 0]
 
-    # Add median (q_50) from XGBoost prediction
-    df["q_50"] = df["prediction"]
-
     # Calculate a pseudo-standard deviation from the 68% interval width
     df["prediction_std"] = (df["q_84"] - df["q_16"]).abs() / 2.0
 
     # Reorder the quantile columns for easier reading
-    quantile_cols = ["q_025", "q_05", "q_10", "q_16", "q_25", "q_75", "q_84", "q_90", "q_95", "q_975"]
+    quantile_cols = ["q_025", "q_05", "q_10", "q_16", "q_25", "q_50", "q_75", "q_84", "q_90", "q_95", "q_975"]
     other_cols = [col for col in df.columns if col not in quantile_cols]
     df = df[other_cols + quantile_cols]
 
@@ -489,4 +576,14 @@ def predict_fn(df, models) -> pd.DataFrame:
         df["q_95"] = np.maximum(df["q_95"], df["prediction"])
         df["q_975"] = np.maximum(df["q_975"], df["prediction"])
 
+    # Compute confidence scores using pre-computed normalization stats
+    df = compute_confidence(
+        df,
+        lower_q="q_10",
+        upper_q="q_90",
+        alpha=1.0,
+        beta=1.0,
+        median_interval_width=models["median_interval_width"],
+    )
+
     return df

workbench/model_scripts/xgb_model/generated_model_script.py

@@ -0,0 +1,468 @@
+# Imports for XGB Model
+import xgboost as xgb
+import awswrangler as wr
+import numpy as np
+
+# Model Performance Scores
+from sklearn.metrics import (
+    mean_absolute_error,
+    r2_score,
+    root_mean_squared_error,
+    precision_recall_fscore_support,
+    confusion_matrix,
+)
+
+# Classification Encoder
+from sklearn.preprocessing import LabelEncoder
+
+# Scikit Learn Imports
+from sklearn.model_selection import train_test_split
+
+from io import StringIO
+import json
+import argparse
+import joblib
+import os
+import pandas as pd
+from typing import List, Tuple
+
+# Template Parameters
+TEMPLATE_PARAMS = {
+    "model_type": "classifier",
+    "target": "wine_class",
+    "features": ['alcohol', 'malic_acid', 'ash', 'alcalinity_of_ash', 'magnesium', 'total_phenols', 'flavanoids', 'nonflavanoid_phenols', 'proanthocyanins', 'color_intensity', 'hue', 'od280_od315_of_diluted_wines', 'proline'],
+    "compressed_features": [],
+    "model_metrics_s3_path": "s3://sandbox-sageworks-artifacts/models/wine-classification/training",
+    "train_all_data": False,
+    "hyperparameters": {},
+}
+
+
+# Function to check if dataframe is empty
+def check_dataframe(df: pd.DataFrame, df_name: str) -> None:
+    """
+    Check if the provided dataframe is empty and raise an exception if it is.
+
+    Args:
+        df (pd.DataFrame): DataFrame to check
+        df_name (str): Name of the DataFrame
+    """
+    if df.empty:
+        msg = f"*** The training data {df_name} has 0 rows! ***STOPPING***"
+        print(msg)
+        raise ValueError(msg)
+
+
+def expand_proba_column(df: pd.DataFrame, class_labels: List[str]) -> pd.DataFrame:
+    """
+    Expands a column in a DataFrame containing a list of probabilities into separate columns.
+
+    Args:
+        df (pd.DataFrame): DataFrame containing a "pred_proba" column
+        class_labels (List[str]): List of class labels
+
+    Returns:
+        pd.DataFrame: DataFrame with the "pred_proba" expanded into separate columns
+    """
+
+    # Sanity check
+    proba_column = "pred_proba"
+    if proba_column not in df.columns:
+        raise ValueError('DataFrame does not contain a "pred_proba" column')
+
+    # Construct new column names with '_proba' suffix
+    proba_splits = [f"{label}_proba" for label in class_labels]
+
+    # Expand the proba_column into separate columns for each probability
+    proba_df = pd.DataFrame(df[proba_column].tolist(), columns=proba_splits)
+
+    # Drop any proba columns and reset the index in prep for the concat
+    df = df.drop(columns=[proba_column] + proba_splits, errors="ignore")
+    df = df.reset_index(drop=True)
+
+    # Concatenate the new columns with the original DataFrame
+    df = pd.concat([df, proba_df], axis=1)
+    print(df)
+    return df
+
+
+def match_features_case_insensitive(df: pd.DataFrame, model_features: list) -> pd.DataFrame:
+    """
+    Matches and renames DataFrame columns to match model feature names (case-insensitive).
+    Prioritizes exact matches, then case-insensitive matches.
+
+    Raises ValueError if any model features cannot be matched.
+    """
+    df_columns_lower = {col.lower(): col for col in df.columns}
+    rename_dict = {}
+    missing = []
+    for feature in model_features:
+        if feature in df.columns:
+            continue  # Exact match
+        elif feature.lower() in df_columns_lower:
+            rename_dict[df_columns_lower[feature.lower()]] = feature
+        else:
+            missing.append(feature)
+
+    if missing:
+        raise ValueError(f"Features not found: {missing}")
+
+    # Rename the DataFrame columns to match the model features
+    return df.rename(columns=rename_dict)
+
+
+def convert_categorical_types(df: pd.DataFrame, features: list, category_mappings={}) -> tuple:
+    """
+    Converts appropriate columns to categorical type with consistent mappings.
+
+    Args:
+        df (pd.DataFrame): The DataFrame to process.
+        features (list): List of feature names to consider for conversion.
+        category_mappings (dict, optional): Existing category mappings. If empty dict, we're in
+                                            training mode. If populated, we're in inference mode.
+
+    Returns:
+        tuple: (processed DataFrame, category mappings dictionary)
+    """
+    # Training mode
+    if category_mappings == {}:
+        for col in df.select_dtypes(include=["object", "string"]):
+            if col in features and df[col].nunique() < 20:
+                print(f"Training mode: Converting {col} to category")
+                df[col] = df[col].astype("category")
+                category_mappings[col] = df[col].cat.categories.tolist()  # Store category mappings
+
+    # Inference mode
+    else:
+        for col, categories in category_mappings.items():
+            if col in df.columns:
+                print(f"Inference mode: Applying categorical mapping for {col}")
+                df[col] = pd.Categorical(df[col], categories=categories)  # Apply consistent categorical mapping
+
+    return df, category_mappings
+
+
+def decompress_features(
+    df: pd.DataFrame, features: List[str], compressed_features: List[str]
+) -> Tuple[pd.DataFrame, List[str]]:
+    """Prepare features for the model by decompressing bitstring features
+
+    Args:
+        df (pd.DataFrame): The features DataFrame
+        features (List[str]): Full list of feature names
+        compressed_features (List[str]): List of feature names to decompress (bitstrings)
+
+    Returns:
+        pd.DataFrame: DataFrame with the decompressed features
+        List[str]: Updated list of feature names after decompression
+
+    Raises:
+        ValueError: If any missing values are found in the specified features
+    """
+
+    # Check for any missing values in the required features
+    missing_counts = df[features].isna().sum()
+    if missing_counts.any():
+        missing_features = missing_counts[missing_counts > 0]
+        print(
+            f"WARNING: Found missing values in features: {missing_features.to_dict()}. "
+            "WARNING: You might want to remove/replace all NaN values before processing."
+        )
+
+    # Decompress the specified compressed features
+    decompressed_features = features.copy()
+    for feature in compressed_features:
+        if (feature not in df.columns) or (feature not in features):
+            print(f"Feature '{feature}' not in the features list, skipping decompression.")
+            continue
+
+        # Remove the feature from the list of features to avoid duplication
+        decompressed_features.remove(feature)
+
+        # Handle all compressed features as bitstrings
+        bit_matrix = np.array([list(bitstring) for bitstring in df[feature]], dtype=np.uint8)
+        prefix = feature[:3]
+
+        # Create all new columns at once - avoids fragmentation
+        new_col_names = [f"{prefix}_{i}" for i in range(bit_matrix.shape[1])]
+        new_df = pd.DataFrame(bit_matrix, columns=new_col_names, index=df.index)
+
+        # Add to features list
+        decompressed_features.extend(new_col_names)
+
+        # Drop original column and concatenate new ones
+        df = df.drop(columns=[feature])
+        df = pd.concat([df, new_df], axis=1)
+
+    return df, decompressed_features
+
+
+if __name__ == "__main__":
+    """The main function is for training the XGBoost model"""
+
+    # Harness Template Parameters
+    target = TEMPLATE_PARAMS["target"]
+    features = TEMPLATE_PARAMS["features"]
+    orig_features = features.copy()
+    compressed_features = TEMPLATE_PARAMS["compressed_features"]
+    model_type = TEMPLATE_PARAMS["model_type"]
+    model_metrics_s3_path = TEMPLATE_PARAMS["model_metrics_s3_path"]
+    train_all_data = TEMPLATE_PARAMS["train_all_data"]
+    hyperparameters = TEMPLATE_PARAMS["hyperparameters"]
+    validation_split = 0.2
+
+    # Script arguments for input/output directories
+    parser = argparse.ArgumentParser()
+    parser.add_argument("--model-dir", type=str, default=os.environ.get("SM_MODEL_DIR", "/opt/ml/model"))
+    parser.add_argument("--train", type=str, default=os.environ.get("SM_CHANNEL_TRAIN", "/opt/ml/input/data/train"))
+    parser.add_argument(
+        "--output-data-dir", type=str, default=os.environ.get("SM_OUTPUT_DATA_DIR", "/opt/ml/output/data")
+    )
+    args = parser.parse_args()
+
+    # Read the training data into DataFrames
+    training_files = [os.path.join(args.train, file) for file in os.listdir(args.train) if file.endswith(".csv")]
+    print(f"Training Files: {training_files}")
+
+    # Combine files and read them all into a single pandas dataframe
+    all_df = pd.concat([pd.read_csv(file, engine="python") for file in training_files])
+
+    # Check if the dataframe is empty
+    check_dataframe(all_df, "training_df")
+
+    # Features/Target output
+    print(f"Target: {target}")
+    print(f"Features: {str(features)}")
+
+    # Convert any features that might be categorical to 'category' type
+    all_df, category_mappings = convert_categorical_types(all_df, features)
+
+    # If we have compressed features, decompress them
+    if compressed_features:
+        print(f"Decompressing features {compressed_features}...")
+        all_df, features = decompress_features(all_df, features, compressed_features)
+
+    # Do we want to train on all the data?
+    if train_all_data:
+        print("Training on ALL of the data")
+        df_train = all_df.copy()
+        df_val = all_df.copy()
+
+    # Does the dataframe have a training column?
+    elif "training" in all_df.columns:
+        print("Found training column, splitting data based on training column")
+        df_train = all_df[all_df["training"]]
+        df_val = all_df[~all_df["training"]]
+    else:
+        # Just do a random training Split
+        print("WARNING: No training column found, splitting data with random state=42")
+        df_train, df_val = train_test_split(all_df, test_size=validation_split, random_state=42)
+    print(f"FIT/TRAIN: {df_train.shape}")
+    print(f"VALIDATION: {df_val.shape}")
+
+    # Use any hyperparameters to set up both the trainer and model configurations
+    print(f"Hyperparameters: {hyperparameters}")
+
+    # Now spin up our XGB Model
+    if model_type == "classifier":
+        xgb_model = xgb.XGBClassifier(enable_categorical=True, **hyperparameters)
+
+        # Encode the target column
+        label_encoder = LabelEncoder()
+        df_train[target] = label_encoder.fit_transform(df_train[target])
+        df_val[target] = label_encoder.transform(df_val[target])
+
+    else:
+        xgb_model = xgb.XGBRegressor(enable_categorical=True, **hyperparameters)
+        label_encoder = None  # We don't need this for regression
+
+    # Grab our Features, Target and Train the Model
+    y_train = df_train[target]
+    X_train = df_train[features]
+    xgb_model.fit(X_train, y_train)
+
+    # Make Predictions on the Validation Set
+    print(f"Making Predictions on Validation Set...")
+    y_validate = df_val[target]
+    X_validate = df_val[features]
+    preds = xgb_model.predict(X_validate)
+    if model_type == "classifier":
+        # Also get the probabilities for each class
+        print("Processing Probabilities...")
+        probs = xgb_model.predict_proba(X_validate)
+        df_val["pred_proba"] = [p.tolist() for p in probs]
+
+        # Expand the pred_proba column into separate columns for each class
+        print(df_val.columns)
+        df_val = expand_proba_column(df_val, label_encoder.classes_)
+        print(df_val.columns)
+
+        # Decode the target and prediction labels
+        y_validate = label_encoder.inverse_transform(y_validate)
+        preds = label_encoder.inverse_transform(preds)
+
+    # Save predictions to S3 (just the target, prediction, and '_proba' columns)
+    df_val["prediction"] = preds
+    output_columns = [target, "prediction"]
+    output_columns += [col for col in df_val.columns if col.endswith("_proba")]
+    wr.s3.to_csv(
+        df_val[output_columns],
+        path=f"{model_metrics_s3_path}/validation_predictions.csv",
+        index=False,
+    )
+
+    # Report Performance Metrics
+    if model_type == "classifier":
+        # Get the label names and their integer mapping
+        label_names = label_encoder.classes_
+
+        # Calculate various model performance metrics
+        scores = precision_recall_fscore_support(y_validate, preds, average=None, labels=label_names)
+
+        # Put the scores into a dataframe
+        score_df = pd.DataFrame(
+            {
+                target: label_names,
+                "precision": scores[0],
+                "recall": scores[1],
+                "fscore": scores[2],
+                "support": scores[3],
+            }
+        )
+
+        # We need to get creative with the Classification Metrics
+        metrics = ["precision", "recall", "fscore", "support"]
+        for t in label_names:
+            for m in metrics:
+                value = score_df.loc[score_df[target] == t, m].iloc[0]
+                print(f"Metrics:{t}:{m} {value}")
+
+        # Compute and output the confusion matrix
+        conf_mtx = confusion_matrix(y_validate, preds, labels=label_names)
+        for i, row_name in enumerate(label_names):
+            for j, col_name in enumerate(label_names):
+                value = conf_mtx[i, j]
+                print(f"ConfusionMatrix:{row_name}:{col_name} {value}")
+
+    else:
+        # Calculate various model performance metrics (regression)
+        rmse = root_mean_squared_error(y_validate, preds)
+        mae = mean_absolute_error(y_validate, preds)
+        r2 = r2_score(y_validate, preds)
+        print(f"RMSE: {rmse:.3f}")
+        print(f"MAE: {mae:.3f}")
+        print(f"R2: {r2:.3f}")
+        print(f"NumRows: {len(df_val)}")
+
+    # Now save the model to the standard place/name
+    joblib.dump(xgb_model, os.path.join(args.model_dir, "xgb_model.joblib"))
+
+    # Save the label encoder if we have one
+    if label_encoder:
+        joblib.dump(label_encoder, os.path.join(args.model_dir, "label_encoder.joblib"))
+
+    # Save the features (this will validate input during predictions)
+    with open(os.path.join(args.model_dir, "feature_columns.json"), "w") as fp:
+        json.dump(orig_features, fp)  # We save the original features, not the decompressed ones
+
+    # Save the category mappings
+    with open(os.path.join(args.model_dir, "category_mappings.json"), "w") as fp:
+        json.dump(category_mappings, fp)
+
+
+def model_fn(model_dir):
+    """Deserialize and return fitted XGBoost model"""
+    model_path = os.path.join(model_dir, "xgb_model.joblib")
+    model = joblib.load(model_path)
+    return model
+
+
+def input_fn(input_data, content_type):
+    """Parse input data and return a DataFrame."""
+    if not input_data:
+        raise ValueError("Empty input data is not supported!")
+
+    # Decode bytes to string if necessary
+    if isinstance(input_data, bytes):
+        input_data = input_data.decode("utf-8")
+
+    if "text/csv" in content_type:
+        return pd.read_csv(StringIO(input_data))
+    elif "application/json" in content_type:
+        return pd.DataFrame(json.loads(input_data))  # Assumes JSON array of records
+    else:
+        raise ValueError(f"{content_type} not supported!")
+
+
+def output_fn(output_df, accept_type):
+    """Supports both CSV and JSON output formats."""
+    if "text/csv" in accept_type:
+        csv_output = output_df.fillna("N/A").to_csv(index=False)  # CSV with N/A for missing values
+        return csv_output, "text/csv"
+    elif "application/json" in accept_type:
+        return output_df.to_json(orient="records"), "application/json"  # JSON array of records (NaNs -> null)
+    else:
+        raise RuntimeError(f"{accept_type} accept type is not supported by this script.")
+
+
+def predict_fn(df, model) -> pd.DataFrame:
+    """Make Predictions with our XGB Model
+
+    Args:
+        df (pd.DataFrame): The input DataFrame
+        model: The model use for predictions
+
+    Returns:
+        pd.DataFrame: The DataFrame with the predictions added
+    """
+    compressed_features = TEMPLATE_PARAMS["compressed_features"]
+
+    # Grab our feature columns (from training)
+    model_dir = os.environ.get("SM_MODEL_DIR", "/opt/ml/model")
+    with open(os.path.join(model_dir, "feature_columns.json")) as fp:
+        features = json.load(fp)
+    print(f"Model Features: {features}")
+
+    # Load the category mappings (from training)
+    with open(os.path.join(model_dir, "category_mappings.json")) as fp:
+        category_mappings = json.load(fp)
+
+    # Load our Label Encoder if we have one
+    label_encoder = None
+    if os.path.exists(os.path.join(model_dir, "label_encoder.joblib")):
+        label_encoder = joblib.load(os.path.join(model_dir, "label_encoder.joblib"))
+
+    # We're going match features in a case-insensitive manner, accounting for all the permutations
+    # - Model has a feature list that's any case ("Id", "taCos", "cOunT", "likes_tacos")
+    # - Incoming data has columns that are mixed case ("ID", "Tacos", "Count", "Likes_Tacos")
+    matched_df = match_features_case_insensitive(df, features)
+
+    # Detect categorical types in the incoming DataFrame
+    matched_df, _ = convert_categorical_types(matched_df, features, category_mappings)
+
+    # If we have compressed features, decompress them
+    if compressed_features:
+        print("Decompressing features for prediction...")
+        matched_df, features = decompress_features(matched_df, features, compressed_features)
+
+    # Predict the features against our XGB Model
+    X = matched_df[features]
+    predictions = model.predict(X)
+
+    # If we have a label encoder, decode the predictions
+    if label_encoder:
+        predictions = label_encoder.inverse_transform(predictions)
+
+    # Set the predictions on the DataFrame
+    df["prediction"] = predictions
+
+    # Does our model have a 'predict_proba' method? If so we will call it and add the results to the DataFrame
+    if getattr(model, "predict_proba", None):
+        probs = model.predict_proba(matched_df[features])
+        df["pred_proba"] = [p.tolist() for p in probs]
+
+        # Expand the pred_proba column into separate columns for each class
+        df = expand_proba_column(df, label_encoder.classes_)
+
+    # All done, return the DataFrame with new columns for the predictions
+    return df

workbench/repl/workbench_shell.py

@@ -525,7 +525,7 @@ class WorkbenchShell:
     def get_meta(self):
         return self.meta
 
-    def plot_manager(self, data, plot_type: str = "table", **kwargs):
+    def plot_manager(self, data, plot_type: str = "scatter", **kwargs):
         """Plot Manager for Workbench"""
         from workbench.web_interface.components.plugins import ag_table, graph_plot, scatter_plot
 
@@ -564,10 +564,10 @@ class WorkbenchShell:
 
         plugin_test = PluginUnitTest(plugin_class, theme=theme, input_data=data, **kwargs)
 
-        # Run the server and open in the browser
-        plugin_test.run()
+        # Open the browser and run the dash server
         url = f"http://127.0.0.1:{plugin_test.port}"
         webbrowser.open(url)
+        plugin_test.run()
 
 
 # Launch Shell Entry Point